The latest articles on DEV Community by Dk Bk (@dk_bk_578745a78cdd7574ecb). https://dev.to/dk_bk_578745a78cdd7574ecb https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F3960153%2Fb93f43f4-5fc8-45de-a0e7-684a7f12c19f.png https://dev.to/dk_bk_578745a78cdd7574ecb en Dk Bk Sat, 30 May 2026 23:24:10 +0000 https://dev.to/dk_bk_578745a78cdd7574ecb/i-built-an-open-source-ai-agent-governance-kernel-in-3-days-as-a-non-coder-i3i https://dev.to/dk_bk_578745a78cdd7574ecb/i-built-an-open-source-ai-agent-governance-kernel-in-3-days-as-a-non-coder-i3i <p>"Just posted AgentGuard on Hacker News 🛡️<br> AI agent governance kernel — built in 3 days</p> <p>Would mean a lot if you checked it out 🙏</p> <p>You're building with AI agents. Your agent has access to your database, your payments, your users.</p> <p>What happens when it does something it shouldn't?</p> <p>Most startups have no answer. No pause button. No audit trail. No trust scoring. No approval gate. Just an agent with full access and a prayer.</p> <p>AgentGuard changes that.</p> <div class="ltag-github-readme-tag"> <div class="readme-overview"> <h2> <img src="https://assets.dev.to/assets/github-logo-5a155e1f9a670af7944dd5e12375bc76ed542ea80224905ecaf878b9157cdefc.svg" alt="GitHub logo"> <a href="https://github.com/Mangomindai" rel="noopener noreferrer"> Mangomindai </a> / <a href="https://github.com/Mangomindai/agentguard" rel="noopener noreferrer"> agentguard </a> </h2> <h3> AI Agent Governance Kernel — trust, approvals, audit </h3> </div> <div class="ltag-github-body"> <div id="readme" class="md"> <div class="markdown-heading"> <h1 class="heading-element">AgentGuard</h1> </div> <p><strong>AgentGuard is a governance kernel for AI agents — trust scoring, capability tokens, human approval gates, and full audit logs</strong></p> <blockquote> <p><em>"Your AI agents are only as safe as the system governing them."</em></p> </blockquote> <p><a href="https://opensource.org/licenses/MIT" rel="nofollow noopener noreferrer"><img src="https://camo.githubusercontent.com/fdf2982b9f5d7489dcf44570e714e3a15fce6253e0cc6b5aa61a075aac2ff71b/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f4c6963656e73652d4d49542d79656c6c6f772e737667" alt="License: MIT"></a> <a href="https://www.python.org/" rel="nofollow noopener noreferrer"><img src="https://camo.githubusercontent.com/93a33cfc2339ec3fa9be792576576fbaafc42b0c7031285662b02f3aca1e1c59/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f707974686f6e2d332e31302b2d626c75652e737667" alt="Python 3.10+"></a> <a href="https://flask.palletsprojects.com/" rel="nofollow noopener noreferrer"><img src="https://camo.githubusercontent.com/1026905df40f890f893ad59092ff4a2b82382022fa215adbcd85a5aae2bf4ddb/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f666c61736b2d332e782d677265656e2e737667" alt="Flask"></a></p> <div class="markdown-heading"> <h2 class="heading-element">The Problem</h2> </div> <p>You're building with AI agents. Your agent has access to your database, your payments, your users.</p> <p><strong>What happens when it does something it shouldn't?</strong></p> <p>Most startups have no answer. No pause button. No audit trail. No trust scoring. No approval gate. Just an agent with full access and a prayer.</p> <p>AgentGuard changes that.</p> <div class="markdown-heading"> <h2 class="heading-element">What AgentGuard Does</h2> </div> <div class="snippet-clipboard-content notranslate position-relative overflow-auto"> <pre class="notranslate"><code>Agent wants to take an action ↓ AgentGuard checks → Is this agent trusted enough? → Is this action too risky? → Does a human need to approve this? → Is this agent even allowed to act right now? ↓ ALLOW → action proceeds, logged PENDING → paused, human notified for approval BLOCK → stopped, agent trust score drops</code></pre>…</div> </div> </div> <div class="gh-btn-container"><a class="gh-btn" href="https://github.com/Mangomindai/agentguard" rel="noopener noreferrer">View on GitHub</a></div> </div> Dk Bk Sat, 30 May 2026 15:40:50 +0000 https://dev.to/dk_bk_578745a78cdd7574ecb/agentguard-dkbk-is-a-governance-kernel-for-ai-agents-trust-scoring-capability-tokens-human-3f1a https://dev.to/dk_bk_578745a78cdd7574ecb/agentguard-dkbk-is-a-governance-kernel-for-ai-agents-trust-scoring-capability-tokens-human-3f1a <p>try out you fellas who have been scratching their heads to control their agents who have gone rouge. its free for now but if you are kind enough you can drop me few $$$$ would be nice.....try on <a href="https://github.com/Mangomindai/dkbk-kernel" rel="noopener noreferrer">https://github.com/Mangomindai/dkbk-kernel</a><br> <a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fylsmu2qdbsgwnvultshu.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fylsmu2qdbsgwnvultshu.png" alt=" " width="800" height="533"></a></p>